Training in progress, epoch 1

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.7678571428571429,
-    "eval_loss": 0.5364691615104675,
-    "eval_runtime": 0.838,
-    "eval_samples_per_second": 133.654,
-    "eval_steps_per_second": 4.773,
+    "eval_accuracy": 0.42857142857142855,
+    "eval_loss": 0.7569826245307922,
+    "eval_runtime": 0.8506,
+    "eval_samples_per_second": 131.671,
+    "eval_steps_per_second": 4.703,
     "total_flos": 7.471710289148314e+16,
-    "train_loss": 0.3398028165102005,
-    "train_runtime": 91.8361,
-    "train_samples_per_second": 32.732,
-    "train_steps_per_second": 0.261
+    "train_loss": 0.6806501050790151,
+    "train_runtime": 101.6809,
+    "train_samples_per_second": 29.563,
+    "train_steps_per_second": 0.236
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.7678571428571429,
-    "eval_loss": 0.5364691615104675,
-    "eval_runtime": 0.838,
-    "eval_samples_per_second": 133.654,
-    "eval_steps_per_second": 4.773
+    "eval_accuracy": 0.42857142857142855,
+    "eval_loss": 0.7569826245307922,
+    "eval_runtime": 0.8506,
+    "eval_samples_per_second": 131.671,
+    "eval_steps_per_second": 4.703
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20a041664bfab8aecbcd9ad0527ad2e633e0a3720757607ffe7d239ba44ac4a
+oid sha256:dfa2b39739780053001bc48050be7dba4a32c479d2202197326c886a33735db5
 size 110394865

runs/Jul20_22-02-13_fcbe542fc008/events.out.tfevents.1689890902.fcbe542fc008.53766.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edaef4b269f80a29f0560ffc9d9aa3386b5fce5765e90517ce88d57694f221bf
+size 405

runs/Jul20_22-02-13_fcbe542fc008/events.out.tfevents.1689890915.fcbe542fc008.53766.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0436c54c700aa66949e5d71426bcd4b9770649bc3e234ac0ab5659bd7b3a724d
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 7.471710289148314e+16,
-    "train_loss": 0.3398028165102005,
-    "train_runtime": 91.8361,
-    "train_samples_per_second": 32.732,
-    "train_steps_per_second": 0.261
+    "train_loss": 0.6806501050790151,
+    "train_runtime": 101.6809,
+    "train_samples_per_second": 29.563,
+    "train_steps_per_second": 0.236
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.7678571428571429,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-16",
+  "best_metric": 0.42857142857142855,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-8",
   "epoch": 3.0,
   "global_step": 24,
   "is_hyper_param_search": false,
@@ -9,51 +9,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.75,
-      "eval_loss": 0.5683054327964783,
-      "eval_runtime": 0.7946,
-      "eval_samples_per_second": 140.946,
-      "eval_steps_per_second": 5.034,
+      "eval_accuracy": 0.42857142857142855,
+      "eval_loss": 0.7569826245307922,
+      "eval_runtime": 0.8109,
+      "eval_samples_per_second": 138.113,
+      "eval_steps_per_second": 4.933,
       "step": 8
     },
     {
       "epoch": 1.25,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.2735,
+      "loss": 0.7009,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7678571428571429,
-      "eval_loss": 0.5364691615104675,
-      "eval_runtime": 0.8091,
-      "eval_samples_per_second": 138.419,
-      "eval_steps_per_second": 4.944,
+      "eval_accuracy": 0.3125,
+      "eval_loss": 0.8232139945030212,
+      "eval_runtime": 0.7621,
+      "eval_samples_per_second": 146.955,
+      "eval_steps_per_second": 5.248,
       "step": 16
     },
     {
       "epoch": 2.5,
       "learning_rate": 9.523809523809523e-06,
-      "loss": 0.3789,
+      "loss": 0.668,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7678571428571429,
-      "eval_loss": 0.5417876839637756,
-      "eval_runtime": 0.9425,
-      "eval_samples_per_second": 118.834,
-      "eval_steps_per_second": 4.244,
+      "eval_accuracy": 0.26785714285714285,
+      "eval_loss": 0.8589730858802795,
+      "eval_runtime": 0.9029,
+      "eval_samples_per_second": 124.046,
+      "eval_steps_per_second": 4.43,
       "step": 24
     },
     {
       "epoch": 3.0,
       "step": 24,
       "total_flos": 7.471710289148314e+16,
-      "train_loss": 0.3398028165102005,
-      "train_runtime": 91.8361,
-      "train_samples_per_second": 32.732,
-      "train_steps_per_second": 0.261
+      "train_loss": 0.6806501050790151,
+      "train_runtime": 101.6809,
+      "train_samples_per_second": 29.563,
+      "train_steps_per_second": 0.236
     }
   ],
   "max_steps": 24,